Amazon AWS Bedrockproprietary
Released: 2025-11-27Artificial AnalysisNova 2.0 Pro
Nova 2.0 Pro Preview from Amazon, tracked on the Artificial Analysis Intelligence Index.
Intelligence Index
—/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
97tok/sec
Output streaming throughputTime to First Answer
17s
Time to first answer token, including any thinkingCost to Run the Index
—USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Nova 2.0 Pro (Medium configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- —
- Cost to run the Index
- —
- Time per task
- —
- Omniscience index
- —
- Reasoning model
- Yes
- Cached-input price
- $0.312 / 1M
Reasoning & knowledge
- AIME 202589.0%
- CritPt0.0%
- GPQA Diamond78.5%
- Humanity's Last Exam9.4%
- IFBench79.0%
Coding & terminal agents
- LiveCodeBench73.0%
- Terminal-Bench 2.129.6%
- Terminal-Bench Hard24.2%
Agentic work
- GDPval-AA (normalized Elo)477 Elo
- τ²-Bench Telecom92.7%
Long context & documents
Multimodal & science
- MMMU-Pro64.5%
Reasoning-effort variants evaluated
| Variant | Intelligence Index | Cost to run Index | Output speed (tok/s) |
|---|---|---|---|
| Medium | — | — | 97.1 |
| Non-reasoning | — | — | 103.4 |
| Low | — | — | 89.2 |
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Math · AIME 202589.0%
Long context · AA-LCR64.0%
Knowledge · Humanity's Last Exam9.4%
Instruction following · IFBench79.1%
Sourced Benchmark Evaluations (11)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| AIME | Nearing Saturation | 89% | 75 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 78.5% | 78 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 9.4% | 93 | 2026-11-15 | independent | Source ↗ |
| LiveCodeBench | Saturated | 73% | 39 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 64.5% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 79% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 92.7% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 24.2% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 29.6% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 64% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="amazon-nova-2-0-pro-preview",
messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
temperature=0.2
)
print(response.choices[0].message.content)Evaluation & Sourcing Notes
Scores listed for Nova 2.0 Pro represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.